Pith. sign in

REVIEW 1 cited by

Few-Shot Bayesian Optimization with Deep Kernel Surrogates

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2101.07667 v1 pith:EJO2PUS2 submitted 2021-01-19 cs.LG

classification cs.LG
keywords responsedeepoptimizationsurrogatefew-shotfunctionkernellearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Hyperparameter optimization (HPO) is a central pillar in the automation of machine learning solutions and is mainly performed via Bayesian optimization, where a parametric surrogate is learned to approximate the black box response function (e.g. validation error). Unfortunately, evaluating the response function is computationally intensive. As a remedy, earlier work emphasizes the need for transfer learning surrogates which learn to optimize hyperparameters for an algorithm from other tasks. In contrast to previous work, we propose to rethink HPO as a few-shot learning problem in which we train a shared deep surrogate model to quickly adapt (with few response evaluations) to the response function of a new task. We propose the use of a deep kernel network for a Gaussian process surrogate that is meta-learned in an end-to-end fashion in order to jointly approximate the response functions of a collection of training data sets. As a result, the novel few-shot optimization of our deep kernel surrogate leads to new state-of-the-art results at HPO compared to several recent methods on diverse metadata sets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 6 citations worldwide. Full citation record

  1. Efficient Visual Appearance Optimization by Learning from Prior Preferences

    cs.HC 2025-07 conditional novelty 6.0 of 10

    Meta-PO transfers prior users' preference models through weighted Bayesian optimization, helping new users find desired image or lighting appearances in about 4 to 8 iterations instead of 7 to 10.

Pith tools